{"id":"https://openalex.org/W2207685884","doi":"https://doi.org/10.1109/bigdata.2015.7364065","title":"Data quality issues in big data","display_name":"Data quality issues in big data","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2207685884","doi":"https://doi.org/10.1109/bigdata.2015.7364065","mag":"2207685884"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7364065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018391400","display_name":"Dhana Rao","orcid":null},"institutions":[{"id":"https://openalex.org/I186335123","display_name":"East Carolina University","ror":"https://ror.org/01vx35703","country_code":"US","type":"education","lineage":["https://openalex.org/I186335123"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dhana Rao","raw_affiliation_strings":["Department of Biology, East Carolina University, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Department of Biology, East Carolina University, North Carolina, USA","institution_ids":["https://openalex.org/I186335123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079085412","display_name":"Venkat N. Gudivada","orcid":"https://orcid.org/0000-0001-6704-1657"},"institutions":[{"id":"https://openalex.org/I186335123","display_name":"East Carolina University","ror":"https://ror.org/01vx35703","country_code":"US","type":"education","lineage":["https://openalex.org/I186335123"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkat N Gudivada","raw_affiliation_strings":["Department of Computer Science, East Carolina University, North Carolina, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, East Carolina University, North Carolina, USA","institution_ids":["https://openalex.org/I186335123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023699325","display_name":"Vijay V. Raghavan","orcid":"https://orcid.org/0000-0001-7224-7828"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay V. Raghavan","raw_affiliation_strings":["Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Computer Studies, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018391400"],"corresponding_institution_ids":["https://openalex.org/I186335123"],"apc_list":null,"apc_paid":null,"fwci":2.4035,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.89622777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2654","last_page":"2660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9926000237464905,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8806662559509277},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.7702845931053162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7001807689666748},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6828961968421936},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6569196581840515},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.6154066324234009},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.61060631275177},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5794422626495361},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5051823258399963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.29845064878463745},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12457677721977234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10733991861343384}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8806662559509277},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.7702845931053162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001807689666748},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6828961968421936},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6569196581840515},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.6154066324234009},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.61060631275177},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5794422626495361},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5051823258399963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29845064878463745},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12457677721977234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10733991861343384},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7364065","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7364065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W60554229","https://openalex.org/W110338261","https://openalex.org/W245466107","https://openalex.org/W1103274515","https://openalex.org/W1521736627","https://openalex.org/W1603798699","https://openalex.org/W1835571316","https://openalex.org/W1969709265","https://openalex.org/W1969969393","https://openalex.org/W2001653627","https://openalex.org/W2002690451","https://openalex.org/W2028042751","https://openalex.org/W2032790727","https://openalex.org/W2039548475","https://openalex.org/W2046915831","https://openalex.org/W2049833004","https://openalex.org/W2065753378","https://openalex.org/W2074162075","https://openalex.org/W2078569994","https://openalex.org/W2079106168","https://openalex.org/W2091729411","https://openalex.org/W2099230441","https://openalex.org/W2102697744","https://openalex.org/W2103017472","https://openalex.org/W2115236937","https://openalex.org/W2125816119","https://openalex.org/W2126421772","https://openalex.org/W2126690285","https://openalex.org/W2131660156","https://openalex.org/W2131941936","https://openalex.org/W2134060725","https://openalex.org/W2136049665","https://openalex.org/W2137999759","https://openalex.org/W2150904790","https://openalex.org/W2151580670","https://openalex.org/W2156206665","https://openalex.org/W2165428180","https://openalex.org/W2169049983","https://openalex.org/W2169826929","https://openalex.org/W2952738808","https://openalex.org/W3103751783","https://openalex.org/W6602426905","https://openalex.org/W6604533154","https://openalex.org/W6764799359"],"related_works":["https://openalex.org/W2891888580","https://openalex.org/W2215544391","https://openalex.org/W4210350690","https://openalex.org/W2020045149","https://openalex.org/W2618163531","https://openalex.org/W2548532473","https://openalex.org/W2897583753","https://openalex.org/W2116862600","https://openalex.org/W2398119633","https://openalex.org/W73205277"],"abstract_inverted_index":{"Though":[0],"the":[1,11,16,28,57],"issues":[2,55,66],"of":[3,14,19,30,36],"data":[4,38,53,64,74],"quality":[5,39,54,75],"trace":[6],"back":[7],"their":[8],"origin":[9],"to":[10],"early":[12],"days":[13],"computing,":[15],"recent":[17],"emergence":[18],"Big":[20,31,58],"Data":[21,32,59],"has":[22],"added":[23],"more":[24,43],"dimensions.":[25],"Furthermore,":[26],"given":[27],"range":[29],"applications,":[33],"potential":[34],"consequences":[35],"bad":[37],"can":[40],"be":[41],"for":[42],"disastrous":[44],"and":[45,72],"widespread.":[46],"This":[47],"paper":[48],"provides":[49],"a":[50],"perspective":[51],"on":[52],"in":[56,69],"context.":[60],"it":[61],"also":[62],"discusses":[63],"integration":[65],"that":[67],"arise":[68],"biological":[70],"databases":[71],"attendant":[73],"issues.":[76]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}